add html format, handle lazy loading images

2026-05-24 20:00:45 +00:00 · 2022-08-09 18:21:18 +02:00
parent 97e7d7a5bb
commit d73ae0a73b
8 changed files with 137 additions and 19 deletions
--- a/2
+++ b/2
@@ -2,7 +2,7 @@ format:
 	gofmt -s -w .

 test:
-	go test github.com/lapwat/papeer/book
+	go test ./...

 install:
 	go install
--- a/README.md
+++ b/README.md
@@ -1,6 +1,6 @@
 # Papeer

-Papeer is a powerful **ereader internet vacuum**. It can scrape any website, removing ads and keeping only the relevant content (formatted text and images). You can export the content to Markdown, EPUB or MOBI files.
+Papeer is a powerful **ereader internet vacuum**. It can scrape any website, removing ads and keeping only the relevant content (formatted text and images). You can export the content to Markdown, HTML, EPUB or MOBI files.

 # Table of contents

@@ -39,7 +39,7 @@ Flags:
  -a, --author string      book author
      --delay int          time in milliseconds to wait before downloading next chapter, use with depth/selector (default -1)
  -d, --depth int          scraping depth
-  -f, --format string      file format [stdout, md, epub, mobi] (default "md")
+  -f, --format string      file format [md, html, epub, mobi] (default "md")
  -h, --help               help for get
      --images             retrieve images only
  -i, --include            include URL as first chapter, use with depth/selector
@@ -50,6 +50,7 @@ Flags:
  -q, --quiet              hide progress bar
  -r, --reverse            reverse chapter order
  -s, --selector strings   table of contents CSS selector
+      --stdout             print to standard output
  -t, --threads int        download concurrency, use with depth/selector (default -1)
      --use-link-name      use link name for chapter title
 ```
@@ -140,7 +141,7 @@ go install github.com/lapwat/papeer@latest
 ```sh
 # use platform=darwin for MacOS
 platform=linux
-release=0.5.5
+release=0.5.6

 # download and extract
 curl -L https://github.com/lapwat/papeer/releases/download/v$release/papeer-v$release-$platform-amd64.tar.gz > papeer.tar.gz
@@ -153,7 +154,7 @@ sudo mv papeer /usr/local/bin

 ### Windows

-Download [latest release](https://github.com/lapwat/papeer/releases/download/v0.5.5/papeer-v0.5.5-windows-amd64.exe.zip).
+Download [latest release](https://github.com/lapwat/papeer/releases/download/v0.5.6/papeer-v0.5.6-windows-amd64.zip).

 ## MOBI support

--- a/book/format.go
+++ b/book/format.go
@@ -24,6 +24,7 @@ func Filename(name string) string {
 func ToMarkdownString(c chapter) string {
 	markdown := ""

+	// chapter content
 	if c.config.Include {
 		// title
 		markdown += fmt.Sprintf("%s\n", c.Name())
@@ -37,8 +38,8 @@ func ToMarkdownString(c chapter) string {
 		markdown += fmt.Sprintf("%s\n\n\n", content)
 	}

+	// subchapters content
 	for _, sc := range c.SubChapters() {
-		// subchapters content
 		markdown += fmt.Sprintf("%s\n\n\n", ToMarkdownString(sc))
 	}

@@ -66,6 +67,44 @@ func ToMarkdown(c chapter, filename string) string {
 	return filename
 }

+func ToHtmlString(c chapter) string {
+	html := ""
+
+	// chapter content
+	if c.config.Include {
+		html += fmt.Sprintf("<h1>%s</h1>", c.Name())
+		html += c.Content()
+	}
+
+	// subchapters content
+	for _, sc := range c.SubChapters() {
+		html += ToHtmlString(sc)
+	}
+
+	return html
+}
+
+func ToHtml(c chapter, filename string) string {
+	if len(filename) == 0 {
+		filename = fmt.Sprintf("%s.html", Filename(c.Name()))
+	}
+
+	html := fmt.Sprintf("<html><head></head><body>%s</body></html>", ToHtmlString(c))
+
+	// write to file
+	f, err := os.Create(filename)
+	if err != nil {
+		log.Fatal(err)
+	}
+	_, err2 := f.WriteString(html)
+	if err2 != nil {
+		log.Fatal(err2)
+	}
+	f.Close()
+
+	return filename
+}
+
 func ToEpub(c chapter, filename string) string {
 	if len(filename) == 0 {
 		filename = fmt.Sprintf("%s.epub", Filename(c.Name()))
@@ -88,6 +127,7 @@ func ToEpub(c chapter, filename string) string {
 func AppendToEpub(e *epub.Epub, c chapter) {
 	content := ""

+	// chapter content
 	if c.config.Include {

 		if c.config.ImagesOnly == false {
@@ -129,6 +169,7 @@ func AppendToEpub(e *epub.Epub, c chapter) {

 	}

+	// subchapters content
 	for _, sc := range c.SubChapters() {
 		AppendToEpub(e, sc)
 	}
--- a/book/format_test.go
+++ b/book/format_test.go
@@ -22,7 +22,7 @@ func TestToMarkdownString(t *testing.T) {
 	c := NewChapterFromURL("https://books.lapw.at/", "", []*ScrapeConfig{NewScrapeConfig()}, 0, func(index int, name string) {})

 	got := ToMarkdownString(c)
-	want := "Books\n=====\n\n- [Discours de la Méthode](https://books.lapw.at/posts/ren%C3%A9-descartes-discours-de-la-m%C3%A9thode/)clock 98 min read -\n1637\n\n- [The Twelve-Factor App](https://books.lapw.at/posts/adam-wiggins-the-twelve-factor-app/)clock 22 min read -\n2011\n\n\n"
+	want := "Books\n=====\n\n- [Discours de la Méthode](https://books.lapw.at/posts/ren%C3%A9-descartes-discours-de-la-m%C3%A9thode/)clock 98 min read -\n   1637\n\n- [The Twelve-Factor App](https://books.lapw.at/posts/adam-wiggins-the-twelve-factor-app/)clock 22 min read -\n   2011\n\n\n"

 	if got != want {
 		t.Errorf("got %q, wanted %q", got, want)
@@ -62,6 +62,51 @@ func TestToMarkdownFilename(t *testing.T) {

 }

+func TestToHtmlString(t *testing.T) {
+
+	c := NewChapterFromURL("https://books.lapw.at/", "", []*ScrapeConfig{NewScrapeConfig()}, 0, func(index int, name string) {})
+
+	got := ToHtmlString(c)
+	want := "<h1>Books</h1>\n    \n    <main>\n      \n  <article>\n    \n    <ul>\n      \n        <li>\n          <a href=\"https://books.lapw.at/posts/ren%C3%A9-descartes-discours-de-la-m%C3%A9thode/\">Discours de la Méthode</a>\n          <span>\n            <svg xmlns=\"http://www.w3.org/2000/svg\" width=\"24\" height=\"24\" viewBox=\"0 0 24 24\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"2\" stroke-linecap=\"round\" stroke-linejoin=\"round\">\n  <title>clock</title>\n  <circle cx=\"12\" cy=\"12\" r=\"10\"></circle><polyline points=\"12 6 12 12 16 14\"></polyline>\n</svg> 98 min read -\n            1637\n          </span>\n        </li>\n      \n        <li>\n          <a href=\"https://books.lapw.at/posts/adam-wiggins-the-twelve-factor-app/\">The Twelve-Factor App</a>\n          <span>\n            <svg xmlns=\"http://www.w3.org/2000/svg\" width=\"24\" height=\"24\" viewBox=\"0 0 24 24\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"2\" stroke-linecap=\"round\" stroke-linejoin=\"round\">\n  <title>clock</title>\n  <circle cx=\"12\" cy=\"12\" r=\"10\"></circle><polyline points=\"12 6 12 12 16 14\"></polyline>\n</svg> 22 min read -\n            2011\n          </span>\n        </li>\n      \n    </ul>\n    \n\n\n\n  </article>\n\n    </main>\n  \n\n"
+
+	if got != want {
+		t.Errorf("got %q, wanted %q", got, want)
+	}
+
+}
+
+func TestToHtml(t *testing.T) {
+
+	c := NewChapterFromURL("https://books.lapw.at/", "", []*ScrapeConfig{NewScrapeConfig()}, 0, func(index int, name string) {})
+	ToHtml(c, "")
+
+	filename := "Books.html"
+	if _, err := os.Stat(filename); errors.Is(err, os.ErrNotExist) {
+		t.Errorf("%s does not exist: %v", filename, err)
+	} else {
+		if err := os.Remove(filename); err != nil {
+			t.Errorf("cannot remove %v: %v", filename, err)
+		}
+	}
+
+}
+
+func TestToHtmlFilename(t *testing.T) {
+
+	filename := "ebook.html"
+	c := NewChapterFromURL("https://books.lapw.at/", "", []*ScrapeConfig{NewScrapeConfig()}, 0, func(index int, name string) {})
+	ToHtml(c, filename)
+
+	if _, err := os.Stat(filename); errors.Is(err, os.ErrNotExist) {
+		t.Errorf("%s does not exist: %v", filename, err)
+	} else {
+		if err := os.Remove(filename); err != nil {
+			t.Errorf("cannot remove %v: %v", filename, err)
+		}
+	}
+
+}
+
 func TestToEpub(t *testing.T) {

 	c := NewChapterFromURL("https://books.lapw.at/", "", []*ScrapeConfig{NewScrapeConfig()}, 0, func(index int, name string) {})
--- a/book/scraper.go
+++ b/book/scraper.go
@@ -250,27 +250,42 @@ func NewChapterFromURL(url, linkName string, configs []*ScrapeConfig, index int,
 		// we care about the content only if:
 		// - we include this level
 		// - we use the page name
-		content = article.Content
+
+		// parse HTML
+		doc, err := goquery.NewDocumentFromReader(strings.NewReader(article.Content))
+		if err != nil {
+			log.Fatal(err)
+		}
+
+		// handle lazy images
+		doc.Find("img").Each(func(i int, source *goquery.Selection) {
+			src, exists := source.Attr("data-lazy-src")
+			if exists {
+				source.SetAttr("src", src)
+			}
+		})
+		doc.Find("source").Remove()

 		// extract images
 		if config.ImagesOnly {

-			// parse HTML
-			doc, err := goquery.NewDocumentFromReader(strings.NewReader(content))
-			if err != nil {
-				log.Fatal(err)
-			}
-
 			// append every image to content
 			content = ""
 			doc.Find("img").Each(func(i int, s *goquery.Selection) {
 				imageTag, _ := goquery.OuterHtml(s)
-				imageTag = strings.ReplaceAll(imageTag, "\n", "")
-
+				// imageTag = strings.ReplaceAll(imageTag, "\n", "")
 				content += imageTag
 			})

+		} else {
+
+			content, err = doc.Find("[id*=readability-page]").Html()
+			if err != nil {
+				log.Fatal(err)
+			}
+
 		}
+
 	}

 	return chapter{string(body), name, article.Byline, content, subchapters, config}
--- a/book/scraper_test.go
+++ b/book/scraper_test.go
@@ -68,7 +68,7 @@ func TestContent(t *testing.T) {
 	c := NewChapterFromURL("https://books.lapw.at/", "", []*ScrapeConfig{config}, 0, func(index int, name string) {})

 	got := c.Content()
-	want := "<div id=\"readability-page-1\" class=\"page\">\n    \n    <main>\n      \n  <article>\n    \n    <ul>\n      \n        <li>\n          <a href=\"https://books.lapw.at/posts/ren%C3%A9-descartes-discours-de-la-m%C3%A9thode/\">Discours de la Méthode</a>\n          <span>\n            <svg xmlns=\"http://www.w3.org/2000/svg\" width=\"24\" height=\"24\" viewBox=\"0 0 24 24\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"2\" stroke-linecap=\"round\" stroke-linejoin=\"round\">\n  <title>clock</title>\n  <circle cx=\"12\" cy=\"12\" r=\"10\"></circle><polyline points=\"12 6 12 12 16 14\"></polyline>\n</svg> 98 min read -\n            1637\n          </span>\n        </li>\n      \n        <li>\n          <a href=\"https://books.lapw.at/posts/adam-wiggins-the-twelve-factor-app/\">The Twelve-Factor App</a>\n          <span>\n            <svg xmlns=\"http://www.w3.org/2000/svg\" width=\"24\" height=\"24\" viewBox=\"0 0 24 24\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"2\" stroke-linecap=\"round\" stroke-linejoin=\"round\">\n  <title>clock</title>\n  <circle cx=\"12\" cy=\"12\" r=\"10\"></circle><polyline points=\"12 6 12 12 16 14\"></polyline>\n</svg> 22 min read -\n            2011\n          </span>\n        </li>\n      \n    </ul>\n    \n\n\n\n  </article>\n\n    </main>\n  \n\n</div>"
+	want := "\n    \n    <main>\n      \n  <article>\n    \n    <ul>\n      \n        <li>\n          <a href=\"https://books.lapw.at/posts/ren%C3%A9-descartes-discours-de-la-m%C3%A9thode/\">Discours de la Méthode</a>\n          <span>\n            <svg xmlns=\"http://www.w3.org/2000/svg\" width=\"24\" height=\"24\" viewBox=\"0 0 24 24\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"2\" stroke-linecap=\"round\" stroke-linejoin=\"round\">\n  <title>clock</title>\n  <circle cx=\"12\" cy=\"12\" r=\"10\"></circle><polyline points=\"12 6 12 12 16 14\"></polyline>\n</svg> 98 min read -\n            1637\n          </span>\n        </li>\n      \n        <li>\n          <a href=\"https://books.lapw.at/posts/adam-wiggins-the-twelve-factor-app/\">The Twelve-Factor App</a>\n          <span>\n            <svg xmlns=\"http://www.w3.org/2000/svg\" width=\"24\" height=\"24\" viewBox=\"0 0 24 24\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"2\" stroke-linecap=\"round\" stroke-linejoin=\"round\">\n  <title>clock</title>\n  <circle cx=\"12\" cy=\"12\" r=\"10\"></circle><polyline points=\"12 6 12 12 16 14\"></polyline>\n</svg> 22 min read -\n            2011\n          </span>\n        </li>\n      \n    </ul>\n    \n\n\n\n  </article>\n\n    </main>\n  \n\n"

 	if got != want {
 		t.Errorf("got %v, wanted %v", got, want)
--- a/cmd/get.go
+++ b/cmd/get.go
@@ -43,7 +43,7 @@ func init() {

 	getCmd.PersistentFlags().StringVarP(&getOpts.name, "name", "n", "", "book name (default: page title)")
 	getCmd.PersistentFlags().StringVarP(&getOpts.author, "author", "a", "", "book author")
-	getCmd.PersistentFlags().StringVarP(&getOpts.Format, "format", "f", "md", "file format [md, epub, mobi]")
+	getCmd.PersistentFlags().StringVarP(&getOpts.Format, "format", "f", "md", "file format [md, html, epub, mobi]")
 	getCmd.PersistentFlags().StringVarP(&getOpts.output, "output", "", "", "file name (default: book name)")
 	getCmd.PersistentFlags().BoolVarP(&getOpts.stdout, "stdout", "", false, "print to standard output")
 	getCmd.PersistentFlags().BoolVarP(&getOpts.images, "images", "", false, "retrieve images only")
@@ -74,6 +74,7 @@ var getCmd = &cobra.Command{

 		formatEnum := map[string]bool{
 			"md":   true,
+			"html": true,
 			"epub": true,
 			"mobi": true,
 		}
@@ -178,6 +179,21 @@ var getCmd = &cobra.Command{
 			}
 		}

+		if getOpts.Format == "html" {
+			filename := book.ToHtml(c, getOpts.output)
+
+			if getOpts.stdout {
+				bytesRead, err := ioutil.ReadFile(filename)
+				if err != nil {
+					log.Fatal(err)
+				}
+
+				fmt.Println(string(bytesRead))
+			} else {
+				fmt.Printf("Html saved to \"%s\"\n", filename)
+			}
+		}
+
 		if getOpts.Format == "epub" {
 			filename := book.ToEpub(c, getOpts.output)

--- a/cmd/version.go
+++ b/cmd/version.go
@@ -14,6 +14,6 @@ var versionCmd = &cobra.Command{
 	Use:   "version",
 	Short: "Print the version number of papeer",
 	Run: func(cmd *cobra.Command, args []string) {
-		fmt.Println("papeer v0.5.5")
+		fmt.Println("papeer v0.5.6")
 	},
 }